© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242944
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    눌
    0.39
     ALF
    0.38
    RDF
    0.38
     caud
    0.37
    ABAD
    0.37
    Tint
    0.36
    кает
    0.36
    **.
    0.36
    नु
    0.35
     uncontrollable
    0.35
    POSITIVE LOGITS
     அமெ
    0.41
    <unused37>
    0.41
     Амери
    0.41
     eest
    0.40
     እንዴት
    0.39
    <unused32>
    0.39
    amentos
    0.38
     türk
    0.38
     देखें
    0.38
     Preise
    0.37
    Activations Density 0.000%

    No Known Activations